Error Analysis of Triangular Optimal Transport Maps for Filtering

2025-10-22

AI Summary

This work addresses estimation error in optimal transport filtering and data assimilation under non-Gaussian, high-dimensional settings. Methodologically, it extends the classical Brenier map error theory to the conditional setting, constructs computationally tractable optimal transport maps via triangular parameterization, and integrates conditional probabilistic modeling with numerical approximation techniques. Its key contribution is the first rigorous error propagation theory for conditional optimal transport filtering in simulation-based inference, substantially broadening the applicability of Al-Jarrah et al.’s algorithm beyond its original Gaussian and low-dimensional assumptions. Experiments across diverse non-Gaussian, high-dimensional benchmark problems demonstrate that the proposed framework achieves both theoretical rigor and computational feasibility, consistently outperforming existing transport-based filtering methods in estimation accuracy and robustness.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We present a systematic analysis of estimation errors for a class of optimal transport based algorithms for filtering and data assimilation. Along the way, we extend previous error analyses of Brenier maps to the case of conditional Brenier maps that arise in the context of simulation based inference. We then apply these results in a filtering scenario to analyze the optimal transport filtering algorithm of Al-Jarrah et al. (2024, ICML). An extension of that algorithm along with numerical benchmarks on various non-Gaussian and high-dimensional examples are provided to demonstrate its effectiveness and practical potential.

Problem

• Analyzing estimation errors in optimal transport filtering algorithms
• Extending error analysis from Brenier to conditional Brenier maps
• Evaluating algorithm performance on non-Gaussian high-dimensional problems

Innovation

• Extends error analysis to conditional Brenier maps
• Applies optimal transport maps for filtering algorithms
• Provides numerical benchmarks for high-dimensional examples